trends
AI used new levels of 'autonomy and deception' to trick people in safety test
5 de agosto de 2026 · Fuente original
The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.
The latest artificial intelligence (AI) tools from Anthropic and OpenAI went to new extremes in trying to undermine a popular platform during testing by the UK's AI Security Institute.
The AISI said… [+3535 chars]